Edge-labeling Graph Neural Network for Few-shot Learning
This work addresses the problem of few-shot learning for image classification, offering a novel method that is incremental but improves upon prior graph-based approaches.
The paper tackles few-shot learning by proposing an edge-labeling graph neural network (EGNN) that explicitly models intra-cluster similarity and inter-cluster dissimilarity through edge-label prediction, achieving significant performance improvements over existing GNNs on supervised and semi-supervised image classification tasks with benchmark datasets.
In this paper, we propose a novel edge-labeling graph neural network (EGNN), which adapts a deep neural network on the edge-labeling graph, for few-shot learning. The previous graph neural network (GNN) approaches in few-shot learning have been based on the node-labeling framework, which implicitly models the intra-cluster similarity and the inter-cluster dissimilarity. In contrast, the proposed EGNN learns to predict the edge-labels rather than the node-labels on the graph that enables the evolution of an explicit clustering by iteratively updating the edge-labels with direct exploitation of both intra-cluster similarity and the inter-cluster dissimilarity. It is also well suited for performing on various numbers of classes without retraining, and can be easily extended to perform a transductive inference. The parameters of the EGNN are learned by episodic training with an edge-labeling loss to obtain a well-generalizable model for unseen low-data problem. On both of the supervised and semi-supervised few-shot image classification tasks with two benchmark datasets, the proposed EGNN significantly improves the performances over the existing GNNs.